检索结果-内蒙古大学图书馆

33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Qian Jiachen Nanjing Univ Posts & Telecommun Nanjing Jiangsu Peoples R China

ISBN: (纸本)9781538672556

A two-degree-of-freedom frame-based visual tracking system with image stabilization function and target tracking function is proposed and designed in this paper. By applying MEMS sensor signal processing technology, micro controller-based stepper motor control and electronic image stabilization technology based on grayscale projection, the system has good stability against large angle changes and high-frequency small-amplitude jitter. By combining the Kalman filter in the camshift framework, the target tracking performance in the similar background is improved. The designed visual tracking device has good image stabilization performance and can perform continuously stable tracking when the target color is similar to the background.

关键词： visual tracking mechanical image stabilization electronic image stabilization camshift algorithm Kalman filter

来源：评论

学校读者我要写书评

暂无评论

Maximally Stable Extremal Regions Improved Tracking algorithm Based on Depth Image 1st

Maximally Stable Extremal Regions Improved Tracking Algorith...

引用

1st International Conference on Intelligent Manufacturing and Internet of Things (IMIOT) / 5th International Conference on Computing for Sustainable Energy and Environment (ICSEE)

作者： Wang, Haikuan Xie, Dong Sun, Haoxiang Zhou, Wenju Shanghai Univ Sch Mech Engn & Automat 99 Shangda Rd Shanghai 200444 Peoples R China

ISBN: (纸本)9789811323843;9789811323836

In order to solve the problem that traditional camshift algorithm can easily fail to track overlapping targets and multiple similar depth targets, a new improved maximally stable extremal regions (MSER) algorithm is presented in this paper. Firstly, the suspected target contour is extracted and similarity analysis is performed. Secondly, the improved MSER algorithm is used to confirm the target contour and update the similarity library. Finally, combined with the physical properties unique to the depth image and based on the Kalman filter, it is possible to predict the tracking target's moving position. The experimental results show that the real-time performance and recognition rate are improved, and robustness to the situation of target overlap and occlusion is better with the improved MSER algorithm.

关键词： Depth image MSER algorithm Target tracking camshift algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on Human-Computer Interaction Technology based on Visual User Gesture Recognition

Research on Human-Computer Interaction Technology based on V...

引用

3rd International Conference on Mechatronics Engineering and Information Technology(ICMEIT 2019)

作者： Jianfeng Liao Qun Zhang Jianping You Department of Computer Science Wenhua College College of Computer Science Hubei University of Technology

This paper deeply discusses the general situation, background and application of humancomputer interaction, and proposes a new exploration-one-hand gesture recognition in humancomputer interaction mode, and discusses the main research techniques in detail and comprehensively. The basic framework of vision-based gesture recognition system is studied. The various principles and methods of vision-based gesture positioning, gesture tracking, gesture segmentation and gesture recognition are analyzed. Based on the camshift algorithm and the improved camshift algorithm for gesture tracking, the camshift algorithm cannot solve the large-area motion interference problem when solving complex dynamic changes. Therefore, it is proposed to add Kalman filter to estimate the next state. It proves that more effective gesture tracking is realized. This paper uses a more reasonable method to achieve the correct sense of input gestures through the visual channel by means of computer vision, digital image processing, pattern recognition and other theories and techniques. The response required to achieve natural human-computer interaction.

关键词： Vision User gesture recognition Human-computer interaction camshift algorithm

来源：评论

学校读者我要写书评

暂无评论

OBJECT GRABBING WITH A FIVE-FINGER ROBOT HAND USING TWO-CAMERA VISION 17

OBJECT GRABBING WITH A FIVE-FINGER ROBOT HAND USING TWO-CAME...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Luh, Guan-Chun Chuang, Yu-Chun Ho, Kun-Hung Tatung Univ Dept Mech Engn Taipei Taiwan

ISBN: (纸本)9781538652145

This paper discusses the problem of visual-based object grabbing using a five-finger robotic hand connected to a 4-DoF manipulator on an intelligent mobile robot. The camshift algorithm is used to analyze the dynamic vision acquired by a pair of stereo cameras in three-dimension space. Afterwards, inverse and forward kinematics of manipulator and fingers are performed to drive the robot hand to appropriate position and grab a cup. In addition, a coordinate estimation correction method was proposed to improve the accuracy of the calculated position. The proposed method is validated in several experiments.

关键词： Five-finger robot hand Object grabbing Inverse and forward kinematics camshift algorithm Coordinate estimation correction

来源：评论

学校读者我要写书评

暂无评论

A Novel Multi-vehicle Tracking Method Based on Linked List of Associated Vehicles

A Novel Multi-vehicle Tracking Method Based on Linked List o...

引用

International Conference on Image, Vision and Computing (ICIVC)

作者： Hongtao Wu Ying Meng Shanxi Transportation Technology Research & Development Co. Ltd Taiyuan China

ISBN: (纸本)9781728123264

Vehicle tracking is a hot research direction in the Intelligent Transportation System (ITS). To deal with the traditional camshift algorithm can not achieve multi-vehicle tracking, and tracking-lost of the vehicle under large proportion occlusion, a novel multi-vehicle tracking method based on linked list of associated vehicles is proposed in this paper. In order to initialize the search window, vehicle detection is used to obtain the target vehicle's location and size. Each tracked vehicle establishes a track list to realize multi-vehicle tracking. The algorithm uses Bhattacharyya distance to occlusion identification, and uses Kalman filter to predict the location of vehicles, accurate vehicle tracking can be realized under occlusion. Experimental results show that the algorithm can achieve a robust and accurate vehicle tracking under different traffic.

关键词： Vehicle tracking camshift algorithm Kalman filter Bhattacharyya distance Vehicle tracking vehicle Kalman filters chain table Intelligent transportation systems algorithms tracking

来源：评论

学校读者我要写书评

暂无评论

Research of Moving Target Detection and Tracking Based on Background Difference and camshift

Research of Moving Target Detection and Tracking Based on Ba...

引用

第30届中国控制与决策会议

作者： Jun Xiao Xin Huang College of Information Science and Engineering Northeastern University Shanghai Institute of Satellite Engineering

As one of the hot spots in the field of computer vision research, video object tracking has been widely applied to various fields of science and technology, national defense construction, security monitoring and other national economy, and has great practical value and broad prospects for development. In the aspect of target detection, the motion detection algorithm based on mixed Gaussian background modeling is mainly researched. For Gaussian mixed model parameter initialization, an improved method for initializing the Gaussian background model is proposed. Then, the pixel value of each pixel in the newly input image and the Gaussian distribution of each pixel are detected and matched, and the model is updated. The new Gaussian distribution generation criterion is developed to improve the Gaussian mixture model updating and the foreground pixel detection. For moving target tracking, based on the study of the histogram of the color histogram and the gray gradient histogram, the adaptive multi-feature fusion algorithm is proposed, by calculating the difference between the foreground and the background of each feature of the target, a fusion model of the improved target feature is obtained, which enhances the robustness of the algorithm in multi-vision feature fusion tracking under complex scenes.

关键词： Target detection target tracking background difference camshift algorithm

来源：评论

学校读者我要写书评

暂无评论

Dynamic Human Tracking for Mobile Robot

Dynamic Human Tracking for Mobile Robot

引用

第37届中国控制会议

作者： Li Su Wei Zhu Boyu Wang College of Automation Harbin Engineering University

The movement of the robot adds great difficulty to dynamic human tracking. The traditional method of image stabilization can not remove the error caused by the movement of the human body to the stable image, resulting in low tracking accuracy and low real-time performance. This paper improves on the basis of traditional image stabilization techniques. In this paper, the least squares method is used to fit the position of the human body in the first N frames to infer the position of the human body in the(N + 1)th frame. Subsequently, this paper adopts the method of sub-regional gray projection to separate the positions of the human body in two adjacent frames of images and stabilize the images, which greatly reduces the error caused by the movement of the human body on the stable image distance. In addition, the traditional mobile body tracking method cannot solve the occlusion tracking situation of the target human body while satisfying the real-time performance. In this paper, various strategies such as camshift algorithm, particle filtering method, image stabilization, and cross-frame difference are integrated, and a dynamic evaluation strategy of tracking quality is designed. The strategy can realize the normal tracking of the moving human body in the state of dynamic robot and tracking of the target human body in the occlusion situation.

关键词： Dynamic background Target tracking Background compensation camshift algorithm Particle filter algorithm

来源：评论

学校读者我要写书评

暂无评论

A Novel Lips Detection Method Combined Adaboost algorithm and camshift algorithm

A Novel Lips Detection Method Combined Adaboost Algorithm an...

引用

2012年计算机应用与系统建模国际会议

作者： Wen Feng Chongqing University of Posts and Telecommunications

The lips detection has a very unique role in identification and tracking, voice recognition, lipsreading and so on. This paper proposed a new lips detection method by combined Adaboost algorithm and camshift algorithm. First, detects the lips by the lips classification which trained by Adaboost algorithm, and marks the specific lips location with a rectangular window. Then, makes the lips color region as the tracking color tracked by camshift algorithm, and track the lips position in the next frame. Finally, uses Adaboost algorithm to do lips detection. The new lips detect method overcomes search the entire window just use Adaboost algorithm, greatly improved the accuracy of lips detection.

关键词： component fAdaboost algorithm camshift algorithm lips detection

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Detecting and Tracking System of Moving Target Based on BF533 29

Design and Implementation of Detecting and Tracking System o...

引用

第29届中国控制与决策会议

作者： Hang Li Guidaojiaotong Polytechnic Institute

ISBN: (纸本)9781509046584

With the intensive study in the fields of video surveillance system,robot navigation and smart home appliances etc.,moving target detection and tracking is raised to a new ***533 development board which has a dedicated video processing hardware can solve the problem of large data and real time in image *** difference multiplication method,the matching difference method,and the improved camshift algorithm are adopted in this ***,these approaches are implemented on a net vision tracking system based on *** result shows that the proposed method can detect and track moving target accurately and has high practical value in reality.

关键词： Image Processing Technology BF533 Difference Multiplication camshift algorithm

来源：评论

学校读者我要写书评

暂无评论

The Implementation of Information Processing algorithm for Intelligent Video Surveillance System

引用

AGRO FOOD INDUSTRY HI-TECH 2017年第3期28卷 1788-1791页

作者： Jing Jing-Xia Henan Univ Anim Husb & Econ Dept Informat Engn Zhengzhou Henan Peoples R China

The application of modern intelligent video surveillance system was more and more, and in this paper, an adaptive background model based on color space transformation was constructed and the shadow elimination algorithm was optimized. In particular, when the target detection was completed by the RGB space, the detection of the foreground target would be locked to the active contour rectangle. And its real-time tracking was obtained;the target's shadow brightness information was used in the elimination of HSV space. It could be seen from the analysis of the final policy that the algorithm could achieve the goal of video tracking under the condition of changing the size of the target or occlusion. Compared with the traditional algorithm, it had a good advantage.

关键词： Intelligent video surveillance tracking algorithm information processing camshift algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：